praysimanjuntak/distilbert-cased-lft

README.md

@@ -0,0 +1,89 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-cased-lft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilbert-cased-lft
+
+This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1017
+- Precision: 0.8722
+- Recall: 0.8905
+- F1: 0.8813
+- Accuracy: 0.9764
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.4065 | 100  | 0.1106          | 0.8374    | 0.7969 | 0.8167 | 0.9647   |
+| No log        | 0.8130 | 200  | 0.0926          | 0.8242    | 0.8474 | 0.8356 | 0.9690   |
+| No log        | 1.2195 | 300  | 0.0898          | 0.8325    | 0.8671 | 0.8494 | 0.9704   |
+| No log        | 1.6260 | 400  | 0.0873          | 0.8591    | 0.8614 | 0.8602 | 0.9729   |
+| 0.0943        | 2.0325 | 500  | 0.0829          | 0.8563    | 0.8765 | 0.8662 | 0.9740   |
+| 0.0943        | 2.4390 | 600  | 0.0864          | 0.8656    | 0.8747 | 0.8701 | 0.9746   |
+| 0.0943        | 2.8455 | 700  | 0.0842          | 0.8652    | 0.8761 | 0.8706 | 0.9746   |
+| 0.0943        | 3.2520 | 800  | 0.0875          | 0.8627    | 0.8823 | 0.8724 | 0.9746   |
+| 0.0943        | 3.6585 | 900  | 0.0887          | 0.8564    | 0.8829 | 0.8694 | 0.9744   |
+| 0.0444        | 4.0650 | 1000 | 0.0875          | 0.8801    | 0.8797 | 0.8799 | 0.9763   |
+| 0.0444        | 4.4715 | 1100 | 0.0944          | 0.8516    | 0.8901 | 0.8704 | 0.9746   |
+| 0.0444        | 4.8780 | 1200 | 0.0906          | 0.8607    | 0.8891 | 0.8746 | 0.9752   |
+| 0.0444        | 5.2846 | 1300 | 0.0934          | 0.8706    | 0.8896 | 0.8800 | 0.9765   |
+| 0.0444        | 5.6911 | 1400 | 0.0914          | 0.8784    | 0.8862 | 0.8823 | 0.9765   |
+| 0.0248        | 6.0976 | 1500 | 0.0918          | 0.8796    | 0.8896 | 0.8846 | 0.9772   |
+| 0.0248        | 6.5041 | 1600 | 0.0960          | 0.8711    | 0.8916 | 0.8812 | 0.9765   |
+| 0.0248        | 6.9106 | 1700 | 0.0970          | 0.8678    | 0.8876 | 0.8776 | 0.9763   |
+| 0.0248        | 7.3171 | 1800 | 0.1008          | 0.8690    | 0.8887 | 0.8787 | 0.9759   |
+| 0.0248        | 7.7236 | 1900 | 0.1012          | 0.8650    | 0.8926 | 0.8786 | 0.9759   |
+| 0.0153        | 8.1301 | 2000 | 0.1002          | 0.8715    | 0.8921 | 0.8817 | 0.9762   |
+| 0.0153        | 8.5366 | 2100 | 0.1003          | 0.8749    | 0.8889 | 0.8818 | 0.9763   |
+| 0.0153        | 8.9431 | 2200 | 0.1015          | 0.8680    | 0.8917 | 0.8797 | 0.9760   |
+| 0.0153        | 9.3496 | 2300 | 0.1015          | 0.8716    | 0.8882 | 0.8798 | 0.9764   |
+| 0.0153        | 9.7561 | 2400 | 0.1017          | 0.8722    | 0.8905 | 0.8813 | 0.9764   |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-PERSON",
+    "2": "I-PERSON",
+    "3": "B-ORGANISATION",
+    "4": "I-ORGANISATION",
+    "5": "B-LOCATION",
+    "6": "I-LOCATION"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-LOCATION": 5,
+    "B-ORGANISATION": 3,
+    "B-PERSON": 1,
+    "I-LOCATION": 6,
+    "I-ORGANISATION": 4,
+    "I-PERSON": 2,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df95680fec780c883b2600fb0d081f75e06bed8eef20960745fd06485362af5
+size 260797516

runs/May27_03-19-02_48beaa2b1cd3/events.out.tfevents.1716779944.48beaa2b1cd3.431.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad8c1ffc0646c05311f1e94bef95a6c1539bfcaea06cb4733ad62f495595435
+size 5075

runs/May27_03-19-51_48beaa2b1cd3/events.out.tfevents.1716779992.48beaa2b1cd3.431.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833b259162fc366fafa2fb7c9aa93af6345cdf2803414c02ed418707a79f0b0e
+size 17592

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b806f2233173bb38e18be523e02ab3a69e9359f386dc94d3915edcafbc801dcf
+size 5112